Latent Space 播客：Dyna Robotics 谈 Dyna-2 与世界模型路线
Robots That Predict the Future: Dyna-2, Million-Hour World Models, & the Bitter Lesson of Robotics ...
Dyna Robotics 的 Jason Ma 上播客聊 Dyna-2，机器人看百万小时人类视频后，45 分钟演示就能学新任务，还在餐厅真部署了。
Latent Space 播客邀请 Dyna Robotics 的 Jason Ma 介绍 Dyna-2 世界-动作模型，该模型通过预测未来来指导物理机器人的动作。团队用超过 100 万小时的人类视频做训练，让机器人只需 45 分钟演示就能适应新任务。访谈还讨论了合成数据、自改进世界模型对机器人训练的加速作用，以及智能体框架如何支撑长达一小时的自主工作流。落地方面，Dyna Robotics 已在 Din Tai Fung 餐厅进行真实部署。
Robots That Predict the Future: Dyna-2, Million-Hour World Models, & the Bitter Lesson of Robotics ...
Robots That Predict the Future: Dyna-2, Million-Hour World Models, & the Bitter Lesson of Robotics @DynaRobotics ’s @JasonMa2020 explains how world-action models predict the future to guide physical robot actions, why training on over a million hours of human video lets robots adapt to new tasks with as little as 45 minutes of demonstrations, how synthetic data and self-improving world models could accelerate robotics, why agentic harnesses are enabling hour-long autonomous workflows, and how the Bitter Lesson of scaling, full-stack hardware, and real-world deployments at Din Tai Fung are turning physical AI from impressive demos into useful robots. Your browser does not support the video tag. 🔗 View on Twitter 💬 1 🔄 0 ❤️ 6 👀 422 📊 2 ⚡
